DEP: inconsistent axis default for np.ma.maximum

This does not match np.maximum, which is confusing because the masked
version has no documentation at all. This uses a similar deprecation approach
to gh-8918, noting that the warning is only needed for arrays of more than one
dimension.

The same remarks apply to `np.ma.minimum`

3 files changed, 47 insertions, 14 deletions

diff --git a/numpy/ma/core.py b/numpy/ma/core.py
index c3f80ea27..e1da2832e 100644
--- a/numpy/ma/core.py
+++ b/numpy/ma/core.py
@@ -6383,24 +6383,34 @@ class _extrema_operation(object):
             return self.reduce(a)
         return where(self.compare(a, b), a, b)
 
-    def reduce(self, target, axis=None):
+    def reduce(self, target, axis=np._NoValue):
         "Reduce target along the given axis."
         target = narray(target, copy=False, subok=True)
         m = getmask(target)
-        if axis is not None:
-            kargs = {'axis': axis}
+
+        if axis is np._NoValue and target.ndim > 1:
+            # 2017-05-06, Numpy 1.13.0: warn on axis default
+            warnings.warn(
+                "In the future the default for ma.{0}.reduce will be axis=0, "
+                "not the current None, to match np.{0}.reduce. "
+                "Explicitly pass 0 or None to silence this warning.".format(
+                    self.__name__
+                ),
+                MaskedArrayFutureWarning, stacklevel=2)
+            axis = None
+
+        if axis is not np._NoValue:
+            kwargs = dict(axis=axis)
         else:
-            kargs = {}
-            target = target.ravel()
-            if not (m is nomask):
-                m = m.ravel()
+            kwargs = dict()
+
         if m is nomask:
-            t = self.ufunc.reduce(target, **kargs)
+            t = self.ufunc.reduce(target, **kwargs)
         else:
             target = target.filled(
                 self.fill_value_func(target)).view(type(target))
-            t = self.ufunc.reduce(target, **kargs)
-            m = umath.logical_and.reduce(m, **kargs)
+            t = self.ufunc.reduce(target, **kwargs)
+            m = umath.logical_and.reduce(m, **kwargs)
             if hasattr(t, '_mask'):
                 t._mask = m
             elif m:
@@ -6433,7 +6443,6 @@ class _minimum_operation(_extrema_operation):
 In one argument case, returns the scalar minimum.
         """
         self.ufunc = umath.minimum
-        self.afunc = amin
         self.compare = less
         self.fill_value_func = minimum_fill_value
 
@@ -6447,7 +6456,6 @@ class _maximum_operation(_extrema_operation):
            In one argument case returns the scalar maximum.
         """
         self.ufunc = umath.maximum
-        self.afunc = amax
         self.compare = greater
         self.fill_value_func = maximum_fill_value
 
diff --git a/numpy/ma/tests/test_core.py b/numpy/ma/tests/test_core.py
index f20c9ba52..e72088692 100644
--- a/numpy/ma/tests/test_core.py
+++ b/numpy/ma/tests/test_core.py
@@ -1065,7 +1065,7 @@ class TestMaskedArrayArithmetic(TestCase):
 
         x = arange(4).reshape(2, 2)
         x[-1, -1] = masked
-        assert_equal(maximum.reduce(x), 2)
+        assert_equal(maximum.reduce(x, axis=None), 2)
 
     def test_minimummaximum_func(self):
         a = np.ones((2, 2))
diff --git a/numpy/ma/tests/test_deprecations.py b/numpy/ma/tests/test_deprecations.py
index 6b3c30e04..661e989d8 100644
--- a/numpy/ma/tests/test_deprecations.py
+++ b/numpy/ma/tests/test_deprecations.py
@@ -6,7 +6,7 @@ from __future__ import division, absolute_import, print_function
 import numpy as np
 from numpy.testing import TestCase, run_module_suite, assert_warns
 from numpy.ma.testutils import assert_equal
-
+from numpy.ma.core import MaskedArrayFutureWarning
 
 class TestArgsort(TestCase):
 	""" gh-8701 """
@@ -44,6 +44,31 @@ class TestMinimumMaximum(TestCase):
     def test_maximum(self):
         assert_warns(DeprecationWarning, np.ma.maximum, np.ma.array([1, 2]))
 
+    def test_axis_default(self):
+        # NumPy 1.13, 2017-05-06
+
+        data1d = np.ma.arange(6)
+        data2d = data1d.reshape(2, 3)
+
+        ma_min = np.ma.minimum.reduce
+        ma_max = np.ma.maximum.reduce
+
+        # check that the default axis is still None, but warns on 2d arrays
+        result = assert_warns(MaskedArrayFutureWarning, ma_max, data2d)
+        assert_equal(result, ma_max(data2d, axis=None))
+
+        result = assert_warns(MaskedArrayFutureWarning, ma_min, data2d)
+        assert_equal(result, ma_min(data2d, axis=None))
+
+        # no warnings on 1d, as both new and old defaults are equivalent
+        result = ma_min(data1d)
+        assert_equal(result, ma_min(data1d, axis=None))
+        assert_equal(result, ma_min(data1d, axis=0))
+
+        result = ma_max(data1d)
+        assert_equal(result, ma_max(data1d, axis=None))
+        assert_equal(result, ma_max(data1d, axis=0))
+
 
 if __name__ == "__main__":
     run_module_suite()